lkml.org 
[lkml]   [2015]   [May]   [19]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
/
Date
From
SubjectRe: [RFC PATCH 1/4] x86, mwaitt: add monitorx and mwaitx instruction
On Tue, May 19, 2015 at 04:01:09PM +0800, Huang Rui wrote:
> On AMD Carrizo processors (Family 15h, Model 60h-6fh), there is a new
> feature called MWAITT (Mwait with a timer) as an extension of
> Monitor/Mwait.
>
> MWAITT, another name is MWAITX (MWAIT with extensions), has a configurable
> timer that causes MWAITX to exit on expiration.
>
> Compared with MONITOR/MWAIT, there are minor differences in opcode and
> input parameters.
>
> MWAITX ECX[1]: enable timer if set
> MWAITX EBX[31:0]: max wait time expressed in SW P0 clocks

What's the behavior if you set EBX to some value but don't enable the
timer with ECX? Normal MWAIT?

> The software P0 frequency is the same as the TSC frequency.
>
> Max timeout = EBX/(TSC frequency)

That's max timeout in seconds then.

> Signed-off-by: Huang Rui <ray.huang@amd.com>
> ---
> arch/x86/include/asm/cpufeature.h | 1 +
> arch/x86/include/asm/mwait.h | 25 +++++++++++++++++++++++++
> 2 files changed, 26 insertions(+)
>
> diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h
> index 3d6606f..3ef1f6e 100644
> --- a/arch/x86/include/asm/cpufeature.h
> +++ b/arch/x86/include/asm/cpufeature.h
> @@ -176,6 +176,7 @@
> #define X86_FEATURE_PERFCTR_NB ( 6*32+24) /* NB performance counter extensions */
> #define X86_FEATURE_BPEXT (6*32+26) /* data breakpoint extension */
> #define X86_FEATURE_PERFCTR_L2 ( 6*32+28) /* L2 performance counter extensions */
> +#define X86_FEATURE_MWAITT ( 6*32+29) /* Mwait extension (MonitorX/MwaitX) */
>
> /*
> * Auxiliary flags: Linux defined - For features scattered in various
> diff --git a/arch/x86/include/asm/mwait.h b/arch/x86/include/asm/mwait.h
> index 653dfa7..b91136f 100644
> --- a/arch/x86/include/asm/mwait.h
> +++ b/arch/x86/include/asm/mwait.h
> @@ -23,6 +23,14 @@ static inline void __monitor(const void *eax, unsigned long ecx,
> :: "a" (eax), "c" (ecx), "d"(edx));
> }
>
> +static inline void __monitorx(const void *eax, unsigned long ecx,
> + unsigned long edx)
> +{
> + /* "monitorx %eax, %ecx, %edx;" */
> + asm volatile(".byte 0x0f, 0x01, 0xfa;"

Ah ok, ModRM extension to secondary opcode 0x1. Simply filling out the
empty slots after SWAPGS, RDTSCP, ... :)

> + :: "a" (eax), "c" (ecx), "d"(edx));
> +}
> +
> static inline void __mwait(unsigned long eax, unsigned long ecx)
> {
> /* "mwait %eax, %ecx;" */
> @@ -30,6 +38,14 @@ static inline void __mwait(unsigned long eax, unsigned long ecx)
> :: "a" (eax), "c" (ecx));
> }
>
> +static inline void __mwaitx(unsigned long eax, unsigned long ebx,
> + unsigned long ecx)
> +{
> + /* "mwaitx %eax, %ebx, %ecx;" */
> + asm volatile(".byte 0x0f, 0x01, 0xfb;"
> + :: "a" (eax), "b" (ebx), "c" (ecx));
> +}
> +
> static inline void __sti_mwait(unsigned long eax, unsigned long ecx)
> {
> trace_hardirqs_on();
> @@ -38,6 +54,15 @@ static inline void __sti_mwait(unsigned long eax, unsigned long ecx)
> :: "a" (eax), "c" (ecx));
> }
>
> +static inline void __sti_mwaitx(unsigned long eax, unsigned long ebx,
> + unsigned long ecx)

Please align the argument on the new line to the opening brace:

static inline void __sti_mwaitx(unsigned long eax, unsigned long ebx,
unsigned long ecx)

> +{
> + trace_hardirqs_on();
> + /* "mwaitx %eax, %ebx, %ecx;" */
> + asm volatile("sti; .byte 0x0f, 0x01, 0xfb;"
> + :: "a" (eax), "b" (ebx), "c" (ecx));
> +}
> +
> /*
> * This uses new MONITOR/MWAIT instructions on P4 processors with PNI,
> * which can obviate IPI to trigger checking of need_resched.
> --
> 2.1.0
>

--
Regards/Gruss,
Boris.

ECO tip #101: Trim your mails when you reply.
--


\
 
 \ /
  Last update: 2015-05-19 14:01    [W:0.535 / U:0.100 seconds]
©2003-2020 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site